Towards a Remote Patient Monitoring Platform for Comprehensive Risk Evaluations for People with Diabetic Foot Ulcers.
Gozde CayM G FincoJason GarciaJill L McNitt-GrayDavid G ArmstrongBijan NajafiPublished in: Sensors (Basel, Switzerland) (2024)
Diabetic foot ulcers (DFUs) significantly affect the lives of patients and increase the risk of hospital stays and amputation. We suggest a remote monitoring platform for better DFU care. This system uses digital health metrics (scaled from 0 to 10, where higher scores indicate a greater risk of slow healing) to provide a comprehensive overview through a visual interface. The platform features smart offloading devices that capture behavioral metrics such as offloading adherence, daily steps, and cadence. Coupled with remotely measurable frailty and phenotypic metrics, it offers an in-depth patient profile. Additional demographic data, characteristics of the wound, and clinical parameters, such as cognitive function, were integrated, contributing to a comprehensive risk factor profile. We evaluated the feasibility of this platform with 124 DFU patients over 12 weeks; 39% experienced unfavorable outcomes such as dropout, adverse events, or non-healing. Digital biomarkers were benchmarked (0-10); categorized as low, medium, and high risk for unfavorable outcomes; and visually represented using color-coded radar plots. The initial results of the case reports illustrate the value of this holistic visualization to pinpoint the underlying risk factors for unfavorable outcomes, including a high number of steps, poor adherence, and cognitive impairment. Although future studies are needed to validate the effectiveness of this visualization in personalizing care and improving wound outcomes, early results in identifying risk factors for unfavorable outcomes are promising.
Keyphrases
- end stage renal disease
- healthcare
- chronic kidney disease
- cognitive impairment
- newly diagnosed
- ejection fraction
- high throughput
- case report
- palliative care
- peritoneal dialysis
- systematic review
- emergency department
- public health
- mental health
- metabolic syndrome
- adipose tissue
- social media
- machine learning
- risk factors
- quality improvement
- health information
- climate change
- insulin resistance
- chronic pain
- preterm birth
- deep learning
- patient reported
- case control
- electron microscopy